Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1407 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1060. Min Range: -6.1060
Max Act: 6.1060. Min Act: -0.1700
Data Index: 975490 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1060. Min Range: -6.1060
Max Act: 6.0435. Min Act: -0.1700
Data Index: 3215715 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1060. Min Range: -6.1060
Max Act: 6.0435. Min Act: -0.1700
Data Index: 3732336 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1060. Min Range: -6.1060
Max Act: 6.0123. Min Act: -0.1700
Data Index: 5996310 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.9498. Min Act: -0.1700
Data Index: 270721 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.7623. Min Act: -0.1700
Data Index: 5557612 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.7623. Min Act: -0.1700
Data Index: 635579 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6685. Min Act: -0.1700
Data Index: 883210 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6998. Min Act: -0.1700
Data Index: 5043829 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6373. Min Act: -0.1700
Data Index: 6978350 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6373. Min Act: -0.1700
Data Index: 296068 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6060. Min Act: -0.1700
Data Index: 6188510 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6060. Min Act: -0.1700
Data Index: 418285 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6060. Min Act: -0.1700
Data Index: 86416 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6060. Min Act: -0.1700
Data Index: 4020432 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.6060. Min Act: -0.1700
Data Index: 7422457 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.5435. Min Act: -0.1700
Data Index: 218567 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.5435. Min Act: -0.1700
Data Index: 7542055 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.5435. Min Act: -0.1700
Data Index: 7542057 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1060. Min Range: -6.1060
Max Act: 5.5123. Min Act: -0.1700
Data Index: 5239798 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19